Machine learning models for the differential diagnosis of vascular parkinsonism and Parkinson's disease using [(123)I]FP-CIT SPECT.

PURPOSE: The study's objective was to develop diagnostic predictive models using data from two commonly used [(123)I]FP-CIT SPECT assessment methods: region-of-interest (ROI) analysis and whole-brain voxel-based analysis. METHODS: We included retrospectively 80 patients with vascular parkinsonism (VP) and 164 patients with Parkinson's disease (PD) who underwent [(123)I]FP-CIT SPECT. Nuclear-medicine specialists evaluated the scans and calculated bilateral caudate and putamen [(123)I]FP-CIT uptake and asymmetry indices using BRASS software. Statistical parametric mapping (SPM) was used to compare the radioligand uptake between the two diseases at the voxel level. Quantitative data from these two methods, together with potential confounding factors for dopamine transporter availability (sex, age, disease duration and severity), were used to build predictive models following a tenfold cross-validation scheme. The performance of logistic regression (LR), linear discriminant analysis and support vector machine (SVM) algorithms for ROI data, and their penalized versions for SPM data (penalized LR, penalized discriminant analysis and SVM), were assessed. RESULTS: Significant differences were found in the ROI analysis after covariate correction between VP and PD patients in [(123)I]FP-CIT uptake in the more affected side of the putamen and the ipsilateral caudate. Age, disease duration and severity were also found to be informative in feeding the statistical model. SPM localized significant reductions in [(123)I]FP-CIT uptake in PD with respect to VP in two specular clusters comprising areas corresponding to the left and right striatum. The diagnostic predictive accuracy of the LR model using ROI data was 90.3 % and of the SVM model using SPM data was 90.4 %. CONCLUSION: The predictive models built with ROI data and SPM data from [(123)I]FP-CIT SPECT provide great discrimination accuracy between VP and PD. External validation of these methods is necessary to confirm their applicability across centres.

Low serum uric acid concentration in Parkinson's disease in southern Spain.

BACKGROUND AND PURPOSE: Uric acid (UA) is thought to have an antioxidant effect on the central nervous system and may also prevent cerebral damage induced by oxidative stress. Our study aimed to investigate whether patients with Parkinson's disease (PD) had lower serum UA concentrations than controls and whether UA concentration was related to clinical parameters of the disease. METHODS: We included 161 patients with PD and 178 controls from southern Spain. UA concentration was compared between these two groups. Clinical parameters including severity of the disease were related to serum UA. RESULTS: Patients with PD showed statistically significant lower serum UA concentrations than controls. Serum UA concentration was lower in patients with PD in severe stages (4 and 5) than in those in moderate stage (2) according to the modified Hoehn and Yahr scale. Other clinical parameters were not related to serum UA concentration, except for levodopa equivalent daily dose that was associated with lower serum UA concentration in men. CONCLUSIONS: Our study produced consistent findings that UA might have a protective effect against PD and could influence its clinical progression.

Brain-derived neurotrophic factor G196A polymorphism and clinical features in Parkinson's disease.

OBJECTIVES: Parkinson's disease (PD) is characterized by the dopaminergic neuronal death in substantia nigra, and genetic factors appear to be involved in the pathophysiology of this disease. Brain-derived neurotrophic factor (BDNF) is widely expressed in the central nervous system and is necessary for the survival of dopaminergic neurons in substantia nigra. G196A, a common polymorphism of the BDNF gene, not only affects cognitive and motor processes, but also is associated with various psychiatric disorders. We evaluated whether G196A polymorphism is associated with PD and/or modifies clinical manifestations in PD patients. METHODS: We included 193 PD patients and 300 control subjects. G196A polymorphism was screened by restriction fragment length polymorphism analysis. Clinical features of each patient were examined in detail. The possible association between genotype and clinical characteristics were determined by bivariate and multivariate analyses. RESULTS: The distribution of G196A allele and genotype frequency was similar between PD and control subjects. Clinical characteristics, including Hoehn-Yahr stage, motor symptoms, non-motor symptoms (depression, cognitive dysfunction, psychiatric dysfunctions, and sleep behavior disorder), and dyskinesias, were not associated with this polymorphism. CONCLUSIONS: G196A polymorphism is not a risk factor for PD and does not seem to modify clinical features in PD patients studied here.